Python에서 크롤러 코드를 예시하는 방법

from urllib import request req = request.urlopen("http://www.baidu.com") print(req.read().decode("utf-8"))

req = request.Request(url) #此处url为某个网址 req.add_header(key,value) #key即user-Agent，value即浏览器的版本信息 resp = request.urlopen(req) print(resp.read().decode("utf-8"))

from urllib import parse

postData = parse.urlencode([ (key1,val1), (key2,val2), (keyn,valn) ])

request.urlopen(req,data=postData.encode("utf-8")) #使用postData发送post请求 resp.status #得到请求状态 resp.reason #得到服务器的类型

#-*- coding:utf-8 -*- from bs4 import BeautifulSoup as bs from urllib.request import urlopen import re import ssl #获取维基百科词条信息 ssl._create_default_https_context = ssl._create_unverified_context #全局取消证书验证 #请求URL，并把结果用utf-8编码 req = urlopen("https://en.wikipedia.org/wiki/Main page").read().decode("utf-8") #使用beautifulsoup去解析 soup = bs(req,"html.parser") # print(soup) #获取所有href属性以“/wiki/Special”开头的a标签 urllist = soup.findAll("a",href=re.compile("^/wiki/Special")) for url in urllist: #去除以.jpg或.JPG结尾的链接 if not re.search("\.(jpg|JPG)$",url["href"]): #get_test()输出标签下的所有内容，包括子标签的内容； #string只输出一个内容，若该标签有子标签则输出“none print(url.get_text()+"----->"+url["href"]) # print(url)

$ pip install pymysql

$ python setup.py install

#引入开发包 import pymysql.cursors #获取数据库链接 connection = pymysql.connect(host="localhost", user = 'root', password = '123456', db ='wikiurl', charset = 'utf8mb4') try: #获取会话指针 with connection.cursor() as cursor #创建sql语句 sql = "insert into `tableName`(`urlname`,`urlhref`) values(%s,%s)" #执行SQL语句 cursor.execute(sql,(url.get_text(),"https://en.wikipedia.org"+url["href"])) #提交 connection.commit() finally: #关闭 connection.close()

Disallow：不允许访问 allow：允许访问